qwen38-dspark-moe-256exp is an open-weight model from Yusheng Su, released under Apache License 2.0. Its published files total 2.4 KB.
5-layer DSpark MoE drafter for Qwen3.8-27B with 256 routed experts (width 512, top-10) and one shared expert (2048): Kan Wu's kan/moe-3-qwen38 SpecForge recipe with half the experts, trained from scratch for 3 epochs on RadixArk/Qwen3.8-27B-Regen-Mixture-v1…
Model Card
By Yusheng Su, published under apache-2.0, revision 12954fa9e625.
5-layer DSpark MoE drafter for Qwen3.8-27B with 256 routed experts (width 512, top-10) and one shared expert (2048): Kan Wu's kan/moe-3-qwen38 SpecForge recipe with half the experts, trained from scratch for 3 epochs on RadixArk/Qwen3.8-27B-Regen-Mixture-v1 (global batch 256, lr 5e-4 constant) on one 4x GB300 node. Each finished epoch is a complete servable SGLang export in its own folder: Training curves: https://wandb.ai/milestraining/specforge-5layer-moe-0.5%2Aexperts/runs/qwen38-dspark-moe-256exp-3ep-gb300 Recipe and config: branch exp/qwen38-dspark-moe-256exp-3ep-gb300 of https://github.com/yushengsu-thu/SpecForge
Read Yusheng Su's full model card
5-layer DSpark MoE drafter for Qwen3.8-27B with 256 routed experts (width 512, top-10) and one shared expert (2048):
Kan Wu's kan/moe-3-qwen38 SpecForge recipe with half the experts, trained from scratch for 3 epochs on
RadixArk/Qwen3.8-27B-Regen-Mixture-v1 (global batch 256, lr 5e-4 constant) on one 4x GB300 node.
Each finished epoch is a complete servable SGLang export in its own folder:
| folder | steps | status |
|---|---|---|
epoch1/ |
4,958 | pending |
epoch2/ |
9,916 | pending |
epoch3/ |
14,874 | pending |
Training curves: https://wandb.ai/miles_training/specforge-5layer-moe-0.5%2Aexperts/runs/qwen38-dspark-moe-256exp-3ep-gb300
Recipe and config: branch exp/qwen38-dspark-moe-256exp-3ep-gb300 of https://github.com/yushengsu-thu/SpecForge
Identity and Version
- Repository
- yushengsu/qwen38-dspark-moe-256exp
- Publisher
- Yusheng Su
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 12954fa9e6256f59a85af1cb09bdaa7b7dbb8501
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
2 files, 2.4 KB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| README.md | Documentation | 929 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Released by Yusheng Su through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3.8-27B
Questions About qwen38-dspark-moe-256exp
Can I use qwen38-dspark-moe-256exp commercially?
Yes. qwen38-dspark-moe-256exp is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.